Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

how about the performance on sdxl? #9

Open
wjgaas opened this issue Nov 27, 2023 · 6 comments
Open

how about the performance on sdxl? #9

wjgaas opened this issue Nov 27, 2023 · 6 comments

Comments

@wjgaas
Copy link

wjgaas commented Nov 27, 2023

will you add it on the sdxl model?

@Sierkinhane
Copy link
Collaborator

Hi, I would like to upgrade the model next month.

@C00reNUT
Copy link

that would be great, thank you!

@wjgaas
Copy link
Author

wjgaas commented Dec 22, 2023

Hi, I would like to upgrade the model next month.

do you have any progress in sdxl model?

@wjgaas
Copy link
Author

wjgaas commented Jan 16, 2024

wondering the performance on sdxl ...

@Sierkinhane
Copy link
Collaborator

I apologize for the delay in my response. I have been quite busy lately, and I am uncertain when I will have time to update the model. However, I believe it should be relatively straightforward to incorporate the XL pipeline using diffusers. You can attempt to replace the pretrained weights at here and try to debug ...

@Cominclip
Copy link

Cominclip commented May 24, 2024

wondering the performance on sdxl ...

that would be great, thank you!

We have extended BoxDiff to SDXL, please refer to BoxDiff-XL. Note that the results are unstable when the size of generated images is [512, 512], but the size of [1024, 1024] will take up a large amount of VRAM.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants